Skip to main content
GDELT Cloud turns the public GDELT article stream into a structured database of geopolitical events, clustered stories, and linked people, organizations and places. Events include actors, geography, source evidence and CAMEO+ categories. Entity records connect news coverage to the people and organizations involved; tone describes how they are covered. Query it over REST, or point an agent at the MCP server.

Quickstart

A working call in two minutes, plus the docs MCP server.

API reference

Every endpoint, parameter and value.

​
What you can ask it

​
Explore the data by question

  • What changed in a country or region? Filter coded events by geography and date, then inspect their source stories. See event coding and conflict data for the available categories and evidence.
  • Who is involved, and how are they connected? Search for a person, organization or place, review the resolved entity candidates, and follow linked events and stories. See the analyst guide for a worked investigation.
  • How can an application monitor a topic? Use the REST API or data MCP server for live queries, or create a Monitor for repeated questions and notifications.
For dataset coverage, freshness and known gaps, use the data catalog before comparing countries or building a time series.

​
The one idea worth knowing

Resolve a name before filtering by entity. Search returns candidates; inspect the match and carry its identifier into endpoints that accept it. Identifier spaces and supported filters vary by endpoint, so check the identifier reference before joining news, awards, filings and physical assets. A bare name can match different subsets across datasets.

Investigate an entity across datasets

Resolve an entity and check which identifiers each API surface accepts.

​
What is ours and what we ingest

Core is what we produce — events, stories, entities, tone. We code every event under our own taxonomy from the raw article stream; we do not resell anyone’s event data. Open Feeds are public registries we ingest and resolve onto the same entity spine — SEC filings, GLEIF, USAspending, FRED, Global Energy Monitor, Epoch AI and more. The value we add is the fusion.

Data catalog

Every dataset, its licence, its coverage window, and what it does not cover.
Consistently coded history begins in March 2026. Earlier dates return a near-empty result that reads like a bug and is not — history is being extended backwards.